Manufactured Housing Survey Main Page
The Manufactured Homes Survey (MHS) is conducted by the U.S. Census Bureau and sponsored by the Department of Housing and Urban Development. MHS produces monthly regional estimates of manufactured homes placements, average sales prices, and dealers' inventories and more detailed annual estimates including selected characteristics of new manufactured homes. The statistics on shipments of manufactured homes are produced by the Institute for Building Technology and Safety (IBTS) and published by the Manufactured Housing Institute (MHI).
A manufactured home is defined as a movable dwelling, 8 feet or more wide and 40 feet or more long, designed to be towed on its own chassis, with transportation gear integral to the unit when it leaves the factory, and without need of a permanent foundation. These manufactured homes include multi-wides and expandable manufactured homes. Excluded are travel trailers, motor homes, and modular housing.
The shipments figures are based on reports submitted by manufacturers on the number of manufactured homes actually shipped during the survey month. Shipments to dealers may not necessarily be placed for residential use in the same month as they are shipped. The number of manufactured "homes" used for nonresidential purposes is not known.
The placement and average sales price figures are based on the initial sale to private individuals for residential use. The MHS does not collect data for resales, repossessions, or placements for nonresidential use. Purchases by state, local and federal government agencies (i.e., FEMA) are not included in the survey.
Note that average sales prices of new manufactured homes shown in the tables are reported by dealers who are instructed to include dealer set-up costs. In some cases, there may be additional costs to prepare units for occupancy not included in the sales prices reported.
Beginning in 1980, the average sales prices are computed from data for manufactured homes sold at or before the time they are placed on a site. Prices (values) of manufactured homes leased or sold after placement are not collected. The average sales price computation for manufactured homes placed prior to 1980 included not only the sales price of those sold, but also the intended sales price of those for sale and the value of leased manufactured homes.
The standard Census geographic regions/divisions are used in various tables. States contained in each region/division are as follows:
Northeast
New England
Middle Atlantic
Midwest
East North Central
West North Central
South
South Atlantic
East South Central
West South Central
West
Mountain
Pacific
The methodology for collecting information on new manufactured homes for 1974 through 1979 involved contacting a sample of manufactured home dealers each month within 137 geographic areas or primary sampling units. The dealers were requested to provide data on the number of manufactured homes received from manufacturers, the number placed on a site for residential use, and the number held in inventory.
The methodology used after 1979 involves a monthly sample of new manufactured homes shipped by manufacturers. The dealer to whom the sampled unit was shipped is contacted by telephone and asked about the status of the unit. This is done each month until that unit is reported as placed.
The various estimates which are shown in the tables are based on sample surveys and may differ from statistics which would have been obtained from a complete census using the same schedules and procedures. An estimate based on a sample survey is subject to both sampling error and nonsampling error. The accuracy of a survey result is determined by the joint effects of these errors.
Sampling error reflects the fact that only a particular sample was surveyed rather than the entire population. Each sample selected for the MHS is one of a large number of similar probability samples that, by chance, might have been selected under the same specifications. Estimates derived from the different samples would differ from each other. The standard error, or sampling error, of a survey estimate is a measure of the variation among the estimates from all possible samples and, thus, is a measure of the precision with which an estimate from a particular sample approximates the average from all possible samples.
Estimates of the standard errors have been computed from the sample data for selected statistics. They are presented in the form of relative standard errors. The relative standard error equals the standard error divided by the estimated value to which it refers.
The sample estimate and an estimate of its standard error allow us to construct interval estimates with prescribed confidence that the interval includes the average result of all possible samples with the same size and design. For example, suppose that an estimated 30,000 manufactured homes were placed in a particular month. Further, suppose that the average relative standard error of this estimate is 4 percent. Multiplying 30,000 by .04, we obtain 1,200 as the standard error. This means that we are confident, with 2 chances out of 3 of being correct, that the average estimate from all possible samples of manufactured homes placed during the particular month is between 28,800 and 31,200 homes. To increase the probability to about 9 chances out of 10 that the interval contains the average value over all possible samples (this is called a 90-percent confidence interval), multiply 1,200 by 1.6, yielding limits of 28,080 and 31,920 (30,000 units plus or minus 1,920 units). The average estimate of manufactured homes placed during the specified month may or may not be contained in any one of these computed intervals; but for a particular sample, one can say that the average estimate from all possible samples is included in the constructed interval with a specified confidence of 90 percent.
The relative standard error estimates sampling variation but does not measure all nonsampling error in the data. Nonsampling error consists of both a variance component and a bias component. Bias is the difference, averaged over all possible samples of the same size and design, between the estimate and the true value being estimated. Nonsampling errors are usually attributed to many possible sources: (1) coverage error - failure to accurately represent all population units in the sample, (2) inability to obtain information about all sample cases, (3) response errors, possibly due to definitional difficulties or misreporting, (4) mistakes in recording or coding the data obtained, and (5) other errors of coverage, collection and nonresponse, response, processing, or imputing for missing or inconsistent data. These nonsampling errors also occur in complete censuses. Although no direct measures of these errors have been obtained, precautionary steps have been taken in all phases of the collection, processing, and tabulation of the data to minimize their influence.
For analyzing general trends in the economy, seasonally adjusted data are usually preferred since seasonal adjustment eliminates the effect of changes that normally occur at about the same time and in about the same magnitude every year. For example, suppose that the normal month-to-month change in an unadjusted series between February and March was an increase of 20 percent. Then, an increase in the unadjusted series of less than 20 percent would be viewed as a decrease in the seasonally adjusted series; an increase of exactly 20 percent would be viewed as no change in the adjusted series; and an increase of more than 20 percent would be viewed as an increase in the adjusted series.
The recurring changes in a series that are removed by seasonal adjustment result from such factors as normal changes in weather and differing lengths of months. It should be emphasized that seasonal adjustment does not account for abnormal weather conditions or for year-to-year changes in weather.
Most of the seasonally adjusted series are shown as seasonally adjusted annual rates (SAAR). A SAAR is the seasonally adjusted monthly rate multiplied by 12.
The seasonal adjustment indexes were developed using X-12-ARIMA. X-12-ARIMA is an enhanced version of the X-11-ARIMA seasonal adjustment program.
The X-12-ARIMA program gives summary statistics which are used in determining the adequacy of the seasonal adjustment. A description of X-12-ARIMA appears in "New Capabilities and Methods of the X-12 ARIMA Seasonal Adjustment Program," by David Findley and others, U.S. Census Bureau, which appeared in the Journal of Business & Economic Statistics, April 1998, Vol. 16, No. 2. For more information on X-12-ARIMA see the reference manuals posted on the Census Bureau's web site.
An assumption underlying the seasonal adjustment process is that the original series can be separated into a seasonal component, a trading-day component, a trend-cycle component, and an irregular component. The seasonally adjusted series consists of the trend-cycle and irregular components taken together. The trend-cycle component includes the long-term trend and the business cycle. The irregular component is made up of residual variations, such as the sudden impact of political events and the effects of strikes, unusual weather conditions, reporting and sampling errors, etc.
Seasonal indexes are developed concurrently for each month for shipments, regional estimates of manufactured homes placements and manufactured homes on dealer lots. The seasonally adjusted U.S. total is the sum of the four regional components.
Source: U.S. Census Bureau
Last revised:
May 29, 2008
